Format: application/x-python-code
1 U
2
3 .R�`� � @ s d dl mZ G dd� d�ZdS )� )�ngramsc @ s e Zd Zddd�ZdS )�Corpus� �<s>�</s>c C sZ d| _ t� | _t� | _t� | _|D ]�}|D ]4}| j�|d�d | j|< | j�|d�d | j|< q*| j�|d�d | j|< | j�|d�d | j|< t|g| |g d�}|D ]:}| j d7 _ || jkr�| j| d7 < q�d| j|< q�q"t| j�� �||g } | D ]R}
4 | D ]F} | j |7 _ | j�|
5 | fd�| | j|
6 | f< | j| |7 < �q
7 �qd S )Nr r � ) �n�dictZ
8 vocabularyZunigramsZbigrams�getr �list�keys) �selfZcorpus�alpha� start_symbolZ
9 end_symbol�sentence�wordZgramsZgramZ _vocabulary�wZw2� r �8C:\Users\PC\Pytho\Projects\NLP\brownclustering\corpus.py�__init__ s,
10 zCorpus.__init__N)r r r )�__name__�
11 __module__� __qualname__r r r r r r s r N)Z nltk.utilr r r r r r �<module> s